Summary
FLUX 3 Action is a 7B world-action model that predicts robot actions from a multimodal foundation. The model adapts image, video, and audio learning through joint video-action training and embodiment-specific fine-tuning.
FLUX 3 Action is a 7B world-action model that predicts robot actions from a multimodal foundation. The model adapts image, video, and audio learning through joint video-action training and embodiment-specific fine-tuning.
Robotics developers can investigate fast local control and combine action prediction with a separate reasoning model for difficult planning. Core capabilities include Seven-billion-parameter action model, Robot action prediction, Joint video-action training, and Embodiment-specific fine-tuning.
Public code or model weights are linked from the project, with setup instructions for running or adapting the system. Additional characteristics include Released model weights, Open fine-tuning recipe, Low-latency policy inference, and Hybrid planning-and-control experiments.
Get more likes & reach the top of search results by adding this button on your site!


Get top updates in AI to your inbox every weekend. It's free!